[Feat] add fail category

app.py

@@ -117,6 +117,7 @@ leaderboard_df = original_df.copy()
     finished_eval_queue_df,
     running_eval_queue_df,
     pending_eval_queue_df,
+    failed_eval_queue_df,
 ) = get_evaluation_queue_df(eval_queue, eval_queue_private, EVAL_REQUESTS_PATH, EVAL_COLS)
 
 ## INTERACTION FUNCTIONS
@@ -513,6 +514,17 @@ with demo:
                                 datatype=EVAL_TYPES,
                                 max_rows=5,
                             )
+                    with gr.Accordion(
+                        f"❌ Failed Evaluations ({len(failed_eval_queue_df)})",
+                        open=False,
+                    ):
+                        with gr.Row():
+                            pending_eval_table = gr.components.Dataframe(
+                                value=failed_eval_queue_df,
+                                headers=EVAL_COLS,
+                                datatype=EVAL_TYPES,
+                                max_rows=5,
+                            )
             with gr.Row():
                 gr.Markdown("# ✉️✨ Submit your model here!", elem_classes="markdown-text")
 

src/load_from_hub.py

@@ -123,10 +123,13 @@ def get_evaluation_queue_df(
     pending_list = [e for e in all_evals if e["status"] in ["PENDING", "RERUN"]]
     running_list = [e for e in all_evals if e["status"] == "RUNNING"]
     finished_list = [e for e in all_evals if e["status"].startswith("FINISHED") or e["status"] == "PENDING_NEW_EVAL"]
+    failed_list = [e for e in all_evals if e["status"] == "FAILED"]
     df_pending = pd.DataFrame.from_records(pending_list, columns=cols)
     df_running = pd.DataFrame.from_records(running_list, columns=cols)
     df_finished = pd.DataFrame.from_records(finished_list, columns=cols)
-    return df_finished[cols], df_running[cols], df_pending[cols]
+    df_failed = pd.DataFrame.from_records(failed_list, columns=cols)
+    return df_finished[cols], df_running[cols], df_pending[cols], df_failed[cols]
+
 
 
 def is_model_on_hub(model_name: str, revision: str) -> bool: